Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 341 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.9996. Min Act: -0.1700

Data Index: 533594 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.9058. Min Act: -0.1700

Data Index: 732761 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.9058. Min Act: -0.1700

Data Index: 559237 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.8589. Min Act: -0.1700

Data Index: 599228 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.8276. Min Act: -0.1700

Data Index: 1235430 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.8589. Min Act: -0.1700

Data Index: 165557 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7650. Min Act: -0.1700

Data Index: 1297936 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7807. Min Act: -0.1700

Data Index: 1287536 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7650. Min Act: -0.1700

Data Index: 270861 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7650. Min Act: -0.1700

Data Index: 857537 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7807. Min Act: -0.1700

Data Index: 934297 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.7024. Min Act: -0.1700

Data Index: 396547 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1258054 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6868. Min Act: -0.1700

Data Index: 560496 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6711. Min Act: -0.1700

Data Index: 1308805 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.5772. Min Act: -0.1700

Data Index: 1157195 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6555. Min Act: -0.1700

Data Index: 247439 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6711. Min Act: -0.1700

Data Index: 603200 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1009555 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.9996. Min Range: -3.9996

Max Act: 3.5616. Min Act: -0.1700

Data Index: 880518 (C4 (Web Text))

Max Activating Token Index: 854